@article{maporlmultiagentpostcotrainingfor,
  title = {MAPoRL: Multi-Agent Post-Co-Training for Collaborative Large Language Models with Reinforcement Learning},
  author = {Chanwoo Park and Seungju Han and Xingzhi Guo and Asuman Ozdaglar and Kaiqing Zhang and Joo-Kyung Kim},
  year = {2025},
  eprint = {2502.18439},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2502.18439v1},
}